diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index cf3e17d..289eb02 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -24,11 +24,16 @@ jobs: # Test pipeline minimum Nextflow version - NXF_VER: "23.04.4" steps: + - name: Free Disk Space (Ubuntu) + uses: jlumbroso/free-disk-space@main + with: + tool_cache: true + - name: Check out pipeline code - uses: actions/checkout@v2 + uses: actions/checkout@v4 - name: Check out test data - uses: actions/checkout@v3 + uses: actions/checkout@v4 with: repository: NorwegianVeterinaryInstitute/ALPPACA ref: testdata diff --git a/CHANGELOG.md b/CHANGELOG.md index 9a85b75..abcd0bb 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,6 +1,13 @@ # Changelog +## Version 2.3.1 +- Updated the version of ParSNP to 2.0.3, as of issue #112 +- Updated Panaroo to version 1.3.4 +- Bumped software versions in all reports +- Added gffs as optional output with the command `--output_gffs`, as of issue #113 + + ## Version 2.3.0 - Gubbins have been updated to version 3.3.2, and the `--seed` parameter now sets the seed for both IQ-Tree and Gubbins, as of isse #109 - Added Bakta as a replacement to Prokka in the core gene track, as of issue #54 diff --git a/bin/cgmlst_report.Rmd b/bin/cgmlst_report.Rmd index 67e2bfb..9dfdf5c 100644 --- a/bin/cgmlst_report.Rmd +++ b/bin/cgmlst_report.Rmd @@ -277,7 +277,7 @@ of ALPPACA. ```{r, message=FALSE, warning=FALSE} tool_data <- data.frame( Tool = c("ChewBBACA","R"), - Version = c("3.1.2","4.1.2") + Version = c("3.3.1","4.1.2") ) tool_data %>% diff --git a/bin/core_gene_report.Rmd b/bin/core_gene_report.Rmd index 8f87459..b299b5e 100644 --- a/bin/core_gene_report.Rmd +++ b/bin/core_gene_report.Rmd @@ -189,16 +189,16 @@ lapply(packages, function(x) clean_pkg_version(x)) %>% These are the tools used to run the analysis within the core genome workflow of ALPPACA. ```{r, message=FALSE, warning=FALSE} tool_data <- data.frame( - Tool = c("Prokka", + Tool = c("Bakta", "Panaroo", "Snp-dists", "Snp-sites", "IQTree"), - Version = c("1.14.6", - "1.2.9", + Version = c("1.9.1", + "1.3.4", "0.8.2", "2.5.1", - "2.2.0.3") + "2.2.6") ) tool_data %>% kbl() %>% diff --git a/bin/core_genome_report.Rmd b/bin/core_genome_report.Rmd index 1c4177f..4dc4c84 100644 --- a/bin/core_genome_report.Rmd +++ b/bin/core_genome_report.Rmd @@ -224,12 +224,12 @@ tool_data <- data.frame( "Snp-dists", "Snp-sites", "IQTree"), - Version = c("1.6.1", - "3.2.0", - "0.5", + Version = c("2.0.3", + "3.3.2", + "0.5--1", "0.8.2", "2.5.1", - "2.2.0.3") + "2.2.6") ) tool_data %>% kbl() %>% diff --git a/bin/mapping_report.Rmd b/bin/mapping_report.Rmd index a804266..2648021 100644 --- a/bin/mapping_report.Rmd +++ b/bin/mapping_report.Rmd @@ -196,11 +196,11 @@ tool_data <- data.frame( "Snp-sites", "IQTree"), Version = c("4.6.0", - "3.2.0", + "3.3.2", "0.5", "0.8.2", "2.5.1", - "2.2.0.3") + "2.2.6") ) tool_data %>% kbl() %>% diff --git a/conf/modules.config b/conf/modules.config index 34f4457..7eabf8a 100644 --- a/conf/modules.config +++ b/conf/modules.config @@ -247,7 +247,7 @@ process { path: { "${params.out_dir}/results" }, mode: params.publish_dir_mode, pattern: "*png", - ], + ] ] } withName: 'PANAROO_PANGENOME' { @@ -327,6 +327,15 @@ process { pattern: "bakta.version" ] } + if(params.output_gffs) { + withName: 'BAKTA' { + publishDir = [ + path: { "${params.out_dir}/results/gffs" }, + mode: params.publish_dir_mode, + pattern: "*gff3" + ] + } + } withName: 'REPORT_ANI' { publishDir = [ [ diff --git a/modules/PANAROO.nf b/modules/PANAROO.nf index ffe36c1..7196cfd 100644 --- a/modules/PANAROO.nf +++ b/modules/PANAROO.nf @@ -1,6 +1,6 @@ process PANAROO_QC { - conda (params.enable_conda ? 'bioconda::panaroo=1.2.9' : null) - container 'quay.io/biocontainers/panaroo:1.2.9--pyhdfd78af_0' + conda (params.enable_conda ? 'bioconda::panaroo=1.3.4' : null) + container 'quay.io/biocontainers/panaroo:1.3.4--pyhdfd78af_0' label 'process_high_memory_time' @@ -22,8 +22,8 @@ process PANAROO_QC { } process PANAROO_PANGENOME { - conda (params.enable_conda ? 'bioconda::panaroo=1.2.9' : null) - container 'quay.io/biocontainers/panaroo:1.2.9--pyhdfd78af_0' + conda (params.enable_conda ? 'bioconda::panaroo=1.3.4' : null) + container 'quay.io/biocontainers/panaroo:1.3.4--pyhdfd78af_0' label 'process_high_cpu_time' diff --git a/modules/PARSNP.nf b/modules/PARSNP.nf index 255920c..2c157c1 100644 --- a/modules/PARSNP.nf +++ b/modules/PARSNP.nf @@ -1,6 +1,6 @@ process PARSNP { - conda (params.enable_conda ? 'bioconda::parsnp=1.7.4' : null) - container 'quay.io/biocontainers/parsnp:1.7.4--hdcf5f25_2' + conda (params.enable_conda ? 'bioconda::parsnp=2.0.3' : null) + container 'quay.io/biocontainers/parsnp:2.0.3--hdcf5f25_0' label 'process_long' @@ -15,8 +15,11 @@ process PARSNP { script: """ parsnp --version > parsnp.version - parsnp -d *.fasta -p 4 --skip-phylogeny -u -o results -r $params.parsnp_ref -v -c &> parsnp.log - mv results/* . + parsnp -d *.fasta -p $task.cpus --skip-phylogeny -u -o results -r $params.parsnp_ref -v -c &> parsnp.log + mv results/log/parsnpAligner.log . + mv results/parsnp.ggr . + mv results/parsnp.xmfa . + mv results/parsnp.unalign . harvesttools -x *xmfa -M parsnp_alignment.fasta """ } diff --git a/nextflow.config b/nextflow.config index 050fbf4..f42b3c8 100644 --- a/nextflow.config +++ b/nextflow.config @@ -37,6 +37,7 @@ params { // Core gene analysis options bakta_db = null + output_gffs = null refdb = null clean_mode = "moderate" identity_threshold = 0.98 @@ -157,7 +158,7 @@ manifest { description = 'A Tool for Prokaryotic Phylogeny and Clustering Analysis' mainScript = 'main.nf' nextflowVersion = '!>=23.04.4' - version = '2.3.0' + version = '2.3.1' } // Define variables to prevent local R libraries from conflicting with the container